Researchers have introduced OASIS, a novel visuomotor policy designed to improve robotic manipulation by aligning the observation and action spaces. This approach utilizes SE(3) end-effector trajectory prediction to ensure that intermediate representations inherently understand the rigid-body geometry of actions. By coupling a 3D-aware feature encoder with an SE(3) trajectory predictor, OASIS generates action chunks consistent with rigid-body motion, outperforming existing vision-language-action and world action models in both simulated and real-world experiments. AI
RANK_REASON The cluster contains an academic paper detailing a new method for robotic manipulation.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
